Learning One-Dimensional Geometric Patterns Under One-Sided Random Misclassification Noise
Abstract
Developing the ability to recognize a landmark from a visual image of a robot's current location is a fundamental problem in robotics. We consider the problem of PAC-learning the concept class of geometric patterns where the target geometric pattern is a configuration of k points in the real line. Each instance is a configuration of n points on the real line, where it is labeled according to whether or not it visually resembles the target pattern.
Cite
Text
Goldberg and Goldman. "Learning One-Dimensional Geometric Patterns Under One-Sided Random Misclassification Noise." Annual Conference on Computational Learning Theory, 1994. doi:10.1145/180139.181131Markdown
[Goldberg and Goldman. "Learning One-Dimensional Geometric Patterns Under One-Sided Random Misclassification Noise." Annual Conference on Computational Learning Theory, 1994.](https://mlanthology.org/colt/1994/goldberg1994colt-learning/) doi:10.1145/180139.181131BibTeX
@inproceedings{goldberg1994colt-learning,
title = {{Learning One-Dimensional Geometric Patterns Under One-Sided Random Misclassification Noise}},
author = {Goldberg, Paul W. and Goldman, Sally A.},
booktitle = {Annual Conference on Computational Learning Theory},
year = {1994},
pages = {246-255},
doi = {10.1145/180139.181131},
url = {https://mlanthology.org/colt/1994/goldberg1994colt-learning/}
}